Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1421 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1854. Min Range: -4.1854
Max Act: 4.1854. Min Act: -0.1700
Data Index: 292177 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1854. Min Range: -4.1854
Max Act: 4.1229. Min Act: -0.1700
Data Index: 6490757 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1854. Min Range: -4.1854
Max Act: 4.0916. Min Act: -0.1700
Data Index: 8720051 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1854. Min Range: -4.1854
Max Act: 4.0291. Min Act: -0.1700
Data Index: 2974018 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1854. Min Range: -4.1854
Max Act: 3.9979. Min Act: -0.1700
Data Index: 8209333 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1854. Min Range: -4.1854
Max Act: 3.9979. Min Act: -0.1700
Data Index: 702924 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1854. Min Range: -4.1854
Max Act: 3.9666. Min Act: -0.1700
Data Index: 1868067 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1854. Min Range: -4.1854
Max Act: 3.9666. Min Act: -0.1700
Data Index: 5571281 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1854. Min Range: -4.1854
Max Act: 3.9666. Min Act: -0.1700
Data Index: 938985 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1854. Min Range: -4.1854
Max Act: 3.9353. Min Act: -0.1700
Data Index: 3278532 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1854. Min Range: -4.1854
Max Act: 3.9041. Min Act: -0.1700
Data Index: 8706873 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1854. Min Range: -4.1854
Max Act: 3.9353. Min Act: -0.1700
Data Index: 5614261 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1854. Min Range: -4.1854
Max Act: 3.9041. Min Act: -0.1700
Data Index: 4818147 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1854. Min Range: -4.1854
Max Act: 3.9041. Min Act: -0.1700
Data Index: 780775 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1854. Min Range: -4.1854
Max Act: 3.9041. Min Act: -0.1700
Data Index: 7444757 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1854. Min Range: -4.1854
Max Act: 3.9041. Min Act: -0.1700
Data Index: 2571682 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1854. Min Range: -4.1854
Max Act: 3.9041. Min Act: -0.1700
Data Index: 1632616 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1854. Min Range: -4.1854
Max Act: 3.9041. Min Act: -0.1700
Data Index: 211001 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1854. Min Range: -4.1854
Max Act: 3.9353. Min Act: -0.1700
Data Index: 5639023 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1854. Min Range: -4.1854
Max Act: 3.9041. Min Act: -0.1700
Data Index: 6020043 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19